© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 52020
    Prev
    Next
    INDEX
    Explanations

    threat assessment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parse
    -0.06
     karena
    -0.06
    _group
    -0.06
    *dx
    -0.06
    ATEST
    -0.06
     DM
    -0.06
     buses
    -0.06
    Lesson
    -0.06
     стран
    -0.06
    56
    -0.06
    POSITIVE LOGITS
     wrought
    0.06
     compiled
    0.06
     Pres
    0.06
    passwd
    0.06
    :',
    0.06
    .Cookie
    0.06
    而
    0.06
    周收录
    0.06
     comprehensive
    0.06
    _CANNOT
    0.06
    Activations Density 0.112%

    No Known Activations